Network account security

Abstract

Methods and systems for account access security at a network access device. The method includes receiving data indicating that a particular user has initiated a particular request at an access point; obtaining sensor data that is generated by one or more sensors of the access point proximate to a time that the particular user initiated the particular request; classifying the particular request as a particular type of request; in response to determining that the particular request is classified as the particular type of request, initiating an exception processing mode in which requests that are initiated by the users at the access point result in the generation and output of inaccurate completion data to mimic completion of the request; processing the particular request using the exception processing mode; and providing the inaccurate completion data generated by the access point for the particular request.

The invention claimed is: 
     
       1. A computer-implemented method comprising:
 receiving, by a first device that is operating in a normal operating mode in which requests that are locally initiated by users at the first device are communicated over a network to a second device for completion and that result in generation and output of accurate transaction data by the second device upon completion of a request, data indicating that a particular user has initiated a particular request; 
 obtaining, by the first device, sensor data that is generated by one or more sensors of the first device proximate to a time that the particular user initiated the particular request; 
 classifying, by the first device and using the sensor data, the particular request as a particular type of request; 
 wherein classifying the particular request as the particular type of request comprises:
 identifying, within the sensor data, a first particular type of sound or speech from the particular user; 
 determining that the first particular type of sound or speech includes a positive indication of duress; 
 in response to determining that the first particular type of sound or speech includes a positive indication of duress, confirming the user is under duress by requesting that the user speak a particular phrase; 
 receiving a second particular type of sound or speech from the user speaking the particular phrase; and 
 determining from the second particular type of sound or speech from the user speaking the particular phrase that the user is under duress; 
 
 in response to determining that the particular request is classified as the particular type of request, initiating, by the first device, an exception processing mode in which requests that are initiated by the users at the first device are not communicated over the network to the second device and that result in the generation and output of inaccurate completion data by the first device to mimic completion of the request by the second device; 
 processing, by the first device, the particular request using the exception processing mode; and 
 providing, for output by the first device, the inaccurate completion data generated by the first device for the particular request. 
 
     
     
       2. The method of  claim 1 , wherein classifying the particular request as the particular type of request further comprises determining that the sensor data deviates from second sensor data that was generated by the one or more sensors at a different time prior to the time that the particular user initiated the particular request. 
     
     
       3. The method of  claim 1 , wherein classifying the particular request as the particular type of request further comprises determining a characteristic of the user at the time that the user initiated the particular request. 
     
     
       4. The method of  claim 1 , wherein classifying the particular request as the particular type of request further comprises determining that the sensor data deviates from a baseline set of sensor data. 
     
     
       5. The method of  claim 1 , wherein the sensor data comprises one or more of image data, video data, or audio data. 
     
     
       6. The method of  claim 1 , wherein classifying the particular request as the particular type of request further comprises identifying, within the sensor data, one or more particular types of motions of the particular user. 
     
     
       7. The method of  claim 1 , further comprising in response to determining that the particular request is classified as the particular type of request, providing, for output by the first device, an input request for a particular type of input from the particular user. 
     
     
       8. The method of  claim 1 , wherein the inaccurate completion data comprises a falsification of a particular type of data requested by the particular user in the particular request. 
     
     
       9. The method of  claim 1 , wherein the first device is an automated teller machine (ATM). 
     
     
       10. The method of  claim 1 , wherein the exception processing mode further comprises preventing, by the first device, at least one operation requested by the user in the particular request. 
     
     
       11. The method of  claim 10 , wherein the particular request comprises a withdrawal of funds or a peer-to-peer electronic transfer of funds. 
     
     
       12. The method of  claim 1 , wherein the inaccurate completion data comprises randomly generated account information. 
     
     
       13. The method of  claim 1 , wherein the inaccurate completion data comprises fictitious account information. 
     
     
       14. A system comprising:
 one or more computers and one or more storage devices storing instructions that are 
 operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: 
 receiving, by a first device that is operating in a normal operating mode in which requests that are locally initiated by users at the first device are communicated over a network to a second device for completion and that result in generation and output of accurate transaction data by the second device upon completion of a request, data indicating that a particular user has initiated a particular request; 
 obtaining, by the first device, sensor data that is generated by one or more sensors of the first device proximate to a time that the particular user initiated the particular request; 
 classifying, by the first device and using the sensor data, the particular request as a particular type of request; 
 wherein classifying the particular request as the particular type of request comprises:
 identifying, within the sensor data, a first particular type of sound or speech from the particular user; 
 determining that the first particular type of sound or speech includes a positive indication of duress; 
 in response to determining that the first particular type of sound or speech includes a positive indication of duress, confirming the user is under duress by requesting that the user speak a particular phrase; 
 receiving a second particular type of sound or speech from the user speaking the particular phrase; and 
 determining from the second particular type of sound or speech from the user speaking the particular phrase that the user is under duress; 
 
 in response to determining that the particular request is classified as the particular type of request, initiating, by the first device, an exception processing mode in which requests that are initiated by the users at the first device are not communicated over the network to the second device and that result in the generation and output of inaccurate completion data by the first device to mimic completion of the request by the second device; 
 processing, by the first device, the particular request using the exception processing mode; and 
 providing, for output by the first device, the inaccurate completion data generated by the first device for the particular request. 
 
     
     
       15. The system of  claim 14 , wherein classifying the particular request as the particular type of request further comprises determining that the sensor data deviates from second sensor data that was generated by the one or more sensors at a different time prior to the time that the particular user initiated the particular request. 
     
     
       16. The system of  claim 14 , wherein classifying the particular request as the particular type of request further comprises determining a characteristic of the user at the time that the user initiated the particular request. 
     
     
       17. The system of  claim 14 , wherein the inaccurate completion data comprises a falsification of a particular type of data requested by the particular user in the particular request, and
 wherein the exception processing mode further comprises preventing, by the first device, at least one operation requested by the user in the particular request. 
 
     
     
       18. The system of  claim 14 , wherein the operations further comprise: in response to determining that the particular request is classified as the particular type of request, providing, for output by the first device, an input request for a particular type of input from the particular user. 
     
     
       19. The system of  claim 14 , wherein classifying the particular request as the particular type of request further comprises identifying, within the sensor data, one or more particular types of motions of the particular user. 
     
     
       20. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
 receiving, by a first device that is operating in a normal operating mode in which requests that are locally initiated by users at the first device are communicated over a network to a second device for completion and that result in generation and output of accurate transaction data by the second device upon completion of a request, data indicating that a particular user has initiated a particular request; 
 obtaining, by the first device, sensor data that is generated by one or more sensors of the first device proximate to a time that the particular user initiated the particular request; 
 classifying, by the first device and using the sensor data, the particular request as a particular type of request; 
 wherein classifying the particular request as the particular type of request comprises:
 identifying, within the sensor data, a first particular type of sound or speech from the particular user; 
 determining that the first particular type of sound or speech includes a positive indication of duress; 
 in response to determining that the first particular type of sound or speech includes a positive indication of duress, confirming the user is under duress by requesting that the user speak a particular phrase; 
 receiving a second particular type of sound or speech from the user speaking the particular phrase; and 
 determining from the second particular type of sound or speech from the user speaking the particular phrase that the user is under duress; 
 
 in response to determining that the particular request is classified as the particular type of request, initiating, by the first device, an exception processing mode in which requests that are initiated by the users at the first device are not communicated over the network to the second device and that result in the generation and output of inaccurate completion data by the first device to mimic completion of the request by the second device; 
 processing, by the first device, the particular request using the exception processing mode; and 
 providing, for output by the first device, the inaccurate completion data generated by the first device for the particular request.